NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
NLP 2025 Quiz
ahmed00muhammed0@gmail.com Switch accounts
* Indicates required question
Email *
Record ahmed00muhammed0@gmail.com as the email to be included with my
response
In order to get the length of the string in python, we use * 2 points
length() method
len() method
The pattern /[Cc]at|[Dd]og/ will match * 1 point
Cat
Dog
Both Cat and Dog
Either Cat or Dog
let "x" be a list of elements and "out" is a list of their squares, we want to * 3 points
create a list "y" that contains their cubes using list comprehension.
y = [item*3 for item in x]
y = [item for item in x]
y = [item**2 for item in x]
y = [item**3 for item in x]
1 of 17 4/21/25, 9:11 PM
NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
After executing the following, check all the true choices. * 3 points
dict1 = {'Name': 'Zara', 'Year': 4, 'grade': '67'}
dict1 = {'Name': 'Nageeb'}
dict2 = {'grade': '67'}
dict2 = {'Name': 'Nageeb', 'Year': 4}
dict2 = {'Name': 'Zara', 'Year': 4}
Given all available modes in open() function, check the correct statements. * 3 points
'r' open for reading (default mode)
't' text mode (default)
'w' open for writing, truncating the �le �rst (default mode)
'a' open for writing, appending to the end of the �le if it exists
'b' binary mode
'+' open a disk �le for updating (reading and writing)
From your practice with "re" module, "\w" matches * 1 point
Any alphanumeric or space
Any word character (alphanumeric & underscore)
\d matches any decimal digit, this is equivalent to the class [0-9] * 1 point
True
False
2 of 17 4/21/25, 9:11 PM
NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
In linguistic morphology, _____________ is the process for reducing inflected * 1 point
words to their root form
B. Text-Proo�ng
D. Stemming
A. Rooting
C. Both Rooting & Stemming
In linguistic morphology, _____________ is the process for reducing inflected * 1 point
words to their root form.
c) Text-Proo�ng
b) Rooting
d) Both a & b
a) Stemming
The output of the stemmer is always a valid word. * 1 point
True
False
Choose all true choices about the Bag of Words * 1 point
omits grammar and word order.
is a representation model used to simplify the contents of a selection of text.
is interested in the number of occurrences of words within the text.
does a good job in making sense of text data.
Which represents the concatenation of letters that make up the actual * 1 point
spelling of the word?
Surface level
Lexical level
All of the above
3 of 17 4/21/25, 9:11 PM
NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
gupp(y|ies) matches * 1 point
D) either A) or B)
B) guppy OR ies
A) guppy OR guppies
C) both A) and B)
The following invocation of the match method will return * 3 points
None
Match object from re module
A step which splits longer strings of text into smaller pieces, or tokens is * 1 point
called
Normalization
Tokenization
In order to get the character set ONLY from the following response header * 3 points
we can type
You can open the image in a new tab if it's not clear.
resp.headers.get_content_charset()
resp.headers.get('content-type')
resp.headers.items()
resp.headers.get('content-type').split('=')[0]
resp.headers.get('content-type').split('=')[1]
4 of 17 4/21/25, 9:11 PM
NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
In order to access the web in python and get a text out of it, we could * 2 points
use____________ modules. (Choose all the correct answers)
crawler4j
urllib
coreNLP
BeautifulSoup
pyGad
pattern
requests
scrapy
One of the main challenge/s of NLP is * 1 point
Handling Tokenization
Handling Ambiguity of Sentences
Handling POS-Tagging
All of the above
Which of the following includes major tasks of NLP? * 1 point
A. Machine Translation
B. Automatic Summarization
C. Discourse Analysis
D. All of the above
* اﻟﺴﻜﺸﻦ
section 1
5 of 17 4/21/25, 9:11 PM
NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
If we run the following code, the variable "var" will be * 2 points
a list of hashtags
a list that contains a single string object
a �lter object
/beg.n/ matches * 1 point
begin
beg’n
begun
any character between beg and n
All of the above
What is Morphological Segmentation? * 1 point
a) Does Discourse Analysis
b) Breaks words into individual morphemes and identify the class of the morphemes
c) Is an extension of propositional logic
d) None of the mentioned
One-Hot Encoding Method is better used for * 2 points
Modeling more complex relationships
Bayesian models
Neural networks
General purpose
Syllable is the part of the word that never changes even when * 1 point
morphologically inflected.
True
False
6 of 17 4/21/25, 9:11 PM
NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
Syllables are the smallest meaningful spoken units of language. * 1 point
True
False
Morphology is * 1 point
The study of linguistic sounds and their relations to written words
The study of the structural relationships among words in a sentence
The study of internal structures of words/composition of words
Morphology * 1 point
Analyzes how phrases are formed by smaller phrases and words.
Analyzes how words are formed from minimal units of meaning, or morphemes, e.g.,
dogs= dog+s.
Regular expression is * 1 point
a language for specifying text search strings
doing backtracking to match the string
Check all the true statements about the following code snippet * 1 point
csv_reader() function will be able to handle �les larger than memory size
csv_reader() function will throw MemoryError if the �le is larger than memory size
getcwd() function in os module is used for * 2 points
Get the current working directory
Get the parent directory of a path
Get the parent directory of the current directory
7 of 17 4/21/25, 9:11 PM
NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
Ambiguity in natural language could be * 1 point
Lexical
Syntactic
Semantic
Metonymy
All of the above
Discourse is a linguistic unit that is larger than a single sentence (context) * 1 point
True
False
After running the following commands, Mark the correct from the following * 2 points
options.
dict1 will be {'Name': 'Nageeb'}
dict2 will be {'Name': 'Nageeb'}
dict1 will be {'Name': 'Nageeb', 'Year': 4}
dict2 will be {'Name': 'Nageeb', 'Year': 4}
dict1 will be {'Name': 'Zara', 'Year': 4}
dict2 will be {'Name': 'Zara', 'Year': 4}
Stem is the root of the word together with any derivational affixes to which * 1 point
inflectional affixes are added.
True
False
8 of 17 4/21/25, 9:11 PM
NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
Opening a file with "the with statement" does the following * 3 points
simpli�es exception handling
No need to invoke close() method after getting done with the �le
encapsulating common preparation and cleanup tasks
If we run the following code, the variable "out" will be * 2 points
[['Rafaat', 'omaran'], ['Raheem', 'ahmed'], ['Fawzy', 'mostafa']]
['Rafaat', 'omaran'], ['Raheem', 'ahmed'], ['Fawzy', 'mostafa']
['Rafaat', 'omaran', 'Raheem', 'ahmed', 'Fawzy', 'mostafa']
Given a list of numbers, use map function and lambda expressions to * 3 points
create a list of their squares.
map(lambda var: var**2,seq)
list(map(lambda var: var**2,seq))
list(map(lambda var: var*2,seq))
list(map(lambda var: var,seq))
If we run the following code, the variable "out" will be * 2 points
[['Rafaat', 'omaran'], ['Raheem', 'ahmed'], ['Fawzy', 'mostafa']]
['Rafaat', 'omaran', 'Raheem', 'ahmed', 'Fawzy', 'mostafa']
['Rafaat', 'omaran'], ['Raheem', 'ahmed'], ['Fawzy', 'mostafa']
9 of 17 4/21/25, 9:11 PM
NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
Suppose you are doing bag-of-words text classification on a document. The * 1 point
raw input is a single string containing the text of the entire document.
Choose all possible sentences to describe the pipeline to go from the raw
input to a feature vector.
Tokenization
Training a Naive Bayes model
Normalizing the text
Indexing/word counting
In order to use TF-IDF vectorization method in sklearn we use ______ class * 2 points
Binarizer
T�dfVectorizer
CountVectorizer
Which of the following is Object-oriented programming paradigm? * 2 points
imperative paradigm
declarative paradigm
In the English language inflection morphemes can be * 1 point
Pre�xes, su�xes and in�xes
Circum�xes
Pre�xes only
Pre�xes and su�xes
su�xes only
How is the word "changing" lematized? * 1 point
chan
changin
change
chang
10 of 17 4/21/25, 9:11 PM
NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
Write a regular expression to represent a laughing machine. The laughing * 3 points
machine should recognize sequences of ﻫﻰ, ﻫﻮand ﻫﺎfollowed by !. It
should also recognize any mix of them. Assume separate letters; i.e. و, ا,ﻫـ
ى, the symbol "!" takes the machine to a final state.
$+(![ه]وي:?)^
NLP is concerned with the interactions between computers and human * 1 point
(natural) languages.
False
True
A regexp is NOT a "true" regular expression as long as there is a "\1" (or any * 1 point
number) in the regexp. By regexp, I mean the notion supported by modern
programming languages.
True
False
Lexical level is the representation of the actual spelling of the final word. * 1 point
True
False
From your practice with (RE) module, "\w" matches * 5 points
Any alphanumeric or space
Any word character (alphanumeric & underscore)
Frequency Vectorization Method is better used for * 2 points
Bayesian models
General purpose
Neural networks
Modeling more complex relationships
11 of 17 4/21/25, 9:11 PM
NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
\[Ww]oodchuncks?\ will match woodchuncks, Woodchunks, and * 1 point
woodchunck
True
False
ﻼ ﺑﺎﻟﻠﻐﺔ اﻟﻌﺮﺑﻴﺔ
ً * اﻹﺳﻢ ﻛﺎﻣ
أﺣﻤﺪ ﻣﺤﻤﺪ ﻋﺒﺪاﻟﻌﺎﻃﻲ ﻣﺤﻤﺪ
Distributed Representations Vectorization Methods are better used for * 2 points
General purpose
Neural networks
Bayesian models
Modeling more complex relationships
Text Vectorization is used * 3 points
For reduction of representation space.
To transform our documents into vector representations.
Before applying machine learning algorithm.
/[wh]ood/ will match whood * 1 point
True
False
He lifted the beetle with red cap. contain which type of ambiguity ? * 1 point
A. Lexical ambiguity
D. Syntax Level ambiguity
C. None of the Above
B. Referential ambiguity
12 of 17 4/21/25, 9:11 PM
NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
guppy|ies matches * 1 point
D) either A) or B)
A) guppy OR guppies
C) both A) and B)
B) guppy OR ies
Discourse is a linguistic unit that is larger than a single sentence that * 1 point
represents the context of the text.
True
False
If we run the following code, the variable "out" will be * 2 points
a map object that contains 10, 20, 30
a list of 30,20
a map object that contains 30, 20
a map object that contains 30, 20, 10
Check all true choices about sentence segmentation * 1 point
Sentence tokenization methods work by building a binary classi�er (based on a
sequence of rules or on machine learning).
Sentence segmentation is another important step in text processing.
Segmenting a text into sentences are punctuation, like periods, question marks,
exclamation points.
Sentence segmentation is not the same as sentence tokenization.
os.listdir() will get you only files that's in a directory * 1 point
True
False
13 of 17 4/21/25, 9:11 PM
NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
* اﻟﺮﻗﻢ اﻷﻛﺎدﻳﻨﻤﻲ
4210037
Syllables are often considered the phonological "building blocks" of words. * 1 point
True
False
Which from the following is considered to be a "Natural Language * 1 point
Processing Library"?
SpaCy
Gensim
Scrapy
Requests
Pattern
NLTK
Pandas
Crawler4j
Urllib
BeautifulSoup
TextBlob
CoreNLP
Flask
Write a regular expression that matches the marks in the following text * 4 points
"My degree in NLP course is 100 and my degree in databases course is
99", the regular expression should matches both "100" and "99" from this
text.
\d+ (or [0-9]+)
14 of 17 4/21/25, 9:11 PM
NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
What is Machine Translation? * 1 point
c) Converts any human language to English
b) Converts human language to machine language
a) Converts one human language to another
d) Converts Machine language to human language
TF–IDF Vectorization Method is good for * 2 points
Modeling more complex relationships
Neural networks
Bayesian models
General purpose
Natural language is ______ * 1 point
ambiguous
a collection of morphemes
a sequence of lexemes
Flush() method of the file object do the following * 3 points
Calls close() internally
Writes buffer content to the �le
Clears the buffer without writing the content to the �le
In order to invoke nltk.word_tokenize() * 2 points
We need to download "wordnet" �rst
No need to download any packages
We need to download "punkt" �rst
15 of 17 4/21/25, 9:11 PM
NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
A process step generally refers to a series of related tasks meant to put all * 1 point
text on a level playing field: converting all text to the same case (upper or
lower), removing punctuation, expanding contractions, converting numbers
to their word equivalents, and so on (puts all words on equal footing, and
allows processing to proceed uniformly) is called
Tokenization
Normalization
Given a list of numbers, create the corresponding list that has only even * 4 points
numbers of the input. (P.S. Check all true answers)
list(�lter(lambda item: item%2 != 0,seq))
�lter(lambda item: item%2 == 0,seq)
list(�lter(lambda item: item%2 == 0,seq))
[item for item in seq if item%2 == 0]
[item for item in seq if item%2 != 0]
Phonetics is the study of the structural relationships among words in a * 1 point
sentence.
True
False
\a{4,}h will match ah or aaaah * 1 point
True
False
16 of 17 4/21/25, 9:11 PM
NLP 2025 Quiz https://docs.google.com/forms/d/e/1FAIpQLSeNs0b6FE8BEghKsQa7Lu...
Check all true statements about the following code snippet * 2 points
stop words are returning as a list in NLTK, so we convert it to a set
new_tokens is a list of remaining words after �ltering stop words
This code represent stop words removal in Spacy
This code represent stop words removal in NLTK
The following code represents one of ways to vectorizing the text in NLTK * 1 point
library, which is
Frequency
Word2Vec
Distributed representations
Doc2Vec
TF–IDF
One-hot
Check of the following any lines that returns a "Connection object", given * 1 point
that all the required modules are included.
sqlite3.connect('test.db')
MySQLdb.connect('test.db')
sqlite3.connect('test.db', user='maria', password='python')
MySQLdb.connect('hostname', user='maria', password='python')
Page 1 of 1
Never submit passwords through Google Forms.
This content is neither created nor endorsed by Google. - Terms of Service - Privacy Policy
Does this form look suspicious? Report
Forms
17 of 17 4/21/25, 9:11 PM
